Hazard ratios with confidence intervals

HR = exp(beta) with the interval formed on the LOG scale and exponentiated, so it is asymmetric about the hazard ratio and never crosses zero.

Usage

Hazratio(beta, se, alpha = 0.05, names = NULL)

morie_survival_hr(beta, se, alpha = 0.05, names = NULL)

Arguments

beta: coefficient vector on the log-hazard scale.
se: standard errors of beta.
alpha: significance level.
names: optional names for the coefficients.

Value

list with the hazard ratios, the interval bounds, and the z statistics and p-values.

References

Klein, J. P. and Moeschberger, M. L. (2003). Survival Analysis, 2nd ed., Springer.

Examples

V <- c(1, 2, 3, 4, 5, 6, 7, 8)
Hazratio(V, V)
#> $hazard_ratio
#> [1]    2.718282    7.389056   20.085537   54.598150  148.413159  403.428793
#> [7] 1096.633158 2980.957987
#> 
#> $lower
#> [1] 0.382906676 0.146617523 0.056140828 0.021496698 0.008231229 0.003151793
#> [7] 0.001206842 0.000462108
#> 
#> $upper
#> [1] 1.929728e+01 3.723849e+02 7.186014e+03 1.386705e+05 2.675963e+06
#> [6] 5.163880e+07 9.964882e+08 1.922951e+10
#> 
#> $coef
#> [1] 1 2 3 4 5 6 7 8
#> 
#> $se
#> [1] 1 2 3 4 5 6 7 8
#> 
#> $z
#> [1] 1 1 1 1 1 1 1 1
#> 
#> $p_value
#> [1] 0.3173105 0.3173105 0.3173105 0.3173105 0.3173105 0.3173105 0.3173105
#> [8] 0.3173105
#> 
#> $names
#> NULL
#> 
#> $alpha
#> [1] 0.05
#> 
#> $interval_on_log_scale
#> [1] TRUE
#> 
#> $assumes_proportional_hazards
#> [1] TRUE
#> 
#> $method
#> [1] "HR = exp(beta), interval exponentiated from the log scale"
#>